9-13 July 2018
Sofia, Bulgaria
Europe/Sofia timezone

Adversarial event generator tuning with Bayesian Optimization

9 Jul 2018, 14:15
15m
Hall 9 (National Palace of Culture)

Hall 9

National Palace of Culture

presentation Track 6 – Machine learning and physics analysis T6 - Machine learning and physics analysis

Speaker

Mr Maxim Borisyak (National Research University Higher School of Economics)

Description

High Energy Physics experiments often rely on Monte-Carlo event generators. Such generators often contain a large number of parameters and need fine-tuning to closely match experimentally observed data. This task traditionally requires expert knowledge of the generator and the experimental setup as well as vast computing power.Generative Adversarial Networks (GAN) is a powerful method to match distribution of samples produced by a parametrized generator to a set of observations. Following the recently proposed study on adversarial variational optimization of non-differentiable generator, we adopt Bayesian Optimization as an efficient gradient-free optimization method for adversarial fine-tining of event generators. The proposed method requires minimal prior knowledge,nevertheless, allows for expert insights to be straightforwardly incorporated into the method.In this talk, we briefly describe a theoretical approach to the problem and show the results for parameter tunning of PYTHIA event generator.

Primary authors

Mr Maxim Borisyak (National Research University Higher School of Economics) Radoslav Neychev (National Research University Higher School of Economics) Denis Derkach (National Research University Higher School of Economics) Andrey Ustyuzhanin (National Research University Higher School of Economics)

Presentation Materials